Naive-Deep Face Recognition: Touching the Limit of LFW Benchmark or Not?

Size: px
Start display at page:

Download "Naive-Deep Face Recognition: Touching the Limit of LFW Benchmark or Not?"

Transcription

1 Naive-Deep Face Recognition: Touching the Limit of LFW Benchmark or Not? Erjin Zhou Zhimin Cao Qi Yin Abstract Face recognition performance improves rapidly with the recent deep learning technique developing and underlying large training dataset accumulating. In this paper, we report our observations on how big data impacts the recognition performance. According to these observations, we build our Megvii Face Recognition System, which achieves 99.50% accuracy on the LFW benchmark, outperforming the previous state-of-the-art. Furthermore, we report the performance in a real-world security certification scenario. There still exists a clear gap between machine recognition and human performance. We summarize our experiments and present three challenges lying ahead in recent face recognition. And we indicate several possible solutions towards these challenges. We hope our work will stimulate the community s discussion of the difference between research benchmark and real-world applications. 1. INTRODUCTION The LFW benchmark [8] is intended to test the recognition system s performance in unconstrained environment, which is considerably harder than many other constrained dataset (e.g., YaleB [6] and MultiPIE [7]). It has become the de-facto standard regarding to face-recognition-in-thewild performance evaluation in recent years. Extensive works have been done to push the accuracy limit on it [3, 16, 4, 1, 2, 5, 11, 10, 12, 14, 13, 17, 9]. Throughout the history of LFW benchmark, surprising improvements are obtained with recent deep learning techniques [17, 14, 13, 10, 12]. The main framework of these systems are based on multi-class classification [10, 12, 14, 13]. Meanwhile, many sophisticated methods are developed and applied to recognition systems (e.g., joint Bayesian in [4, 2, 10, 12, 13], model ensemble in [10, 14], multi-stage feature in [10, 12], and joint identification and verification learning in [10, 13]). Indeed, large amounts of outside labeled data are collected for learning deep networks. Unfortunately, there is little work on investigate the relationship between big data and recognition performance Associate-Predict Multiple LE + comp Tom-vs-Pete Bayesian Face Revisited TL Joint Bayesian High-dim LBP DeepID2 GaussianFace Hybrid Deep Learning DeepID FR+FCN DeepID2+ DeepFace Year #Dataset ~ 10K #Dataset < 100K #Dataset > 100K Figure 1. A data perspective to the LFW history. Large amounts of web-collected data is coming up with the recent deep learning waves. Extreme performance improvement is gained then. How does big data impact face recognition? This motivates us to explore how big data impacts the recognition performance. Hence, we collect large amounts of labeled web data, and build a convolutional network framework. Two critical observations are obtained. First, the data distribution and data size do influence the recognition performance. Second, we observe that performance gain by many existing sophisticated methods decreases as total data size increases. According to our observations, we build our Megvii Face Recognition System by simple straightforward convolutional networks without any sophisticated tuning tricks or smart architecture designs. Surprisingly, by utilizing a large web-collected labelled dataset, this naive deep learning system achieves state-of-the-art performance on the LFW. We achieve the 99.50% recognition accuracy, surpassing the human level. Furthermore, we introduce a new benchmark, called Chinese ID (CHID) benchmark, to explore the recognition system s generalization. The CHID benchmark is intended to test the recognition system in a real security certificate environment which constrains on Chinese people 1

2 and requires very low false positive rate. Unfortunately, empirical results show that a generic method trained with webcollected data and high LFW performance doesn t imply an acceptable result on such an application-driven benchmark. When we keep the false positive rate in 10 5, the true positive rateis 66%, which does not meet our application s requirement. By summarizing these experiments, we report three main challenges in face recognition: data bias, very low false positive criteria, and cross factors. Despite we achieve very high accuracy on the LFW benchmark, these problems still exist and will be amplified in many specific real-world applications. Hence, from an industrial perspective, we discuss several ways to direct the future research. Our central concern is around data: how to collect data and how to use data. We hope these discussions will contribute to further study in face recognition. 2. A DATA PERSPECTIVE TO FACE RECOGNITION An interesting view of the LFW benchmark history (see Fig. 1) displays that an implicitly data accumulation underlies the performance improvement. The amount of data expanded 100 times from 2010 to 2014 (e.g., from about 10 thousand training samples in Multiple LE [3] to 4 millions images in DeepFace [14]). Especially, large amounts of web-collected data is coming up with the recent deep learning waves and huge performance improvement is gained then. We are interested in this phenomenon. How does big data, especially the large amounts of web-collected data, impacts the recognition performance? 3. MEGVII FACE RECOGNITION SYSTEM 3.1. Megvii Face Classification Database. We collect and label a large amount of celebrities from Internet, referred to as the Megvii Face Classification (MFC) database. It has 5 million labeled faces with about 20,000 individuals. We delete all the person who appeared in the LFW manually. Fig. 2 (a) shows the distribution of the MFC database, which is a very important characteristic of web-collected data we will describe later Naive deep convolutional neural network. We develop a simple straightforward deep network architecture with multi-class classification on MFC database. The network contains ten layers and the last layer is softmax layer which is set in training phase for supervised learning. The hidden layer output before the softmax layer is taken as the feature of input image. The final representation of the face is followed by a PCA model for feature reduction. Number of instances (a) The Distribution of MFC Database Individual ID (b) Continued Performance Improvement Number of Individuals (c) Long-tail Effect Number of Individuals Figure 2. Data talks. (a) The distribution of the MFC database. All individuals are sorted by the number of instances. (b) Performance under different amounts of training data. The LFW accuracy rises linearly as data size increases. Each sub-training set chooses individuals randomly from the MFC database. (c) Performance under different amounts of training data, meanwhile each sub-database chooses individuals with the largest number of instances. Long-tail effect emerges when number of individuals are greater than 10,000: keep increasing individuals with a few instances per person does not help to improve performance. We measure the similarity between two images through a simple L2 norm. 4. CRITICAL OBSERVATIONS We have conducted a series experiments to explore data impacts on recognition performance. We first investigate how do data size and data distribution influence the system performance. Then we report our observations with many sophisticated techniques appeared in previous literatures, when they come up with large training dataset. All of these experiments are set up with our ten layers CNN, applying to the whole face region Pros and Cons of web-collected data Web-collected data has typical long-tail characteristic: A few rich individuals have many instances, and a lot of individuals are poor with a few instances per person (see Fig. 2(a)). In this section, we first explore how total data size influence the final recognition performance. Then we discuss the long-tail effect in the recognition system. Continued performance improvement. Large amounts of training data improve the system s performance considerably. We investigate this by training the same network with 2

3 different number of individuals from 4,000 to 16,000. The individuals are random sampled from the MFC database. Hence, each sub database keeps the original data distribution. Fig. 2 (b) presents each system s performance on the LFW benchmark. The performance improves linearly as the amounts of data accumulates. Long tail effect. Long tail is a typical characteristic in the web-collected data and we want to know the impact to the system s performance. We first sort all individuals by the number of instances, decreasingly. Then we train the same network with different number of individuals from 4,000 to 16,000. Fig. 2 (c) shows the performance of each systems in the LFW benchmark. Long tail does influence to the performance. The best performance occurs when we take the first 10,000 individuals with the most instances as the training dataset. On the other words, adding the individuals with only a few instances do not help to improve the recognition performance. Indeed, these individuals will further harm the system s performance Traditional tricks fade as data increasing. We have explored many sophisticated methods appeared in previous literatures and observe that as training data increases, little gain is obtained by these methods in our experiments. We have tried: Joint Bayesian: modeling the face representation with independent Gaussian variables [4, 2, 10, 12, 13]; Multi-stage features: combining last several layers outputs as the face representation [10, 12]; Clustering: labeling each individuals with the hierarchical structure and learning with both coarse and fine labels [15]; Joint identification and verification: adding pairwise constrains on the hidden layer of multi-class classification framework [10, 13]. All of these sophisticated methods will introduce extra hyper-parameters to the system, which makes it harder to train. But when we apply these methods to the MFC database by trial and error, according to our experiments, little gain is obtain compared with the simple CNN architecture and PCA reduction. 5. PERFORMANCE EVALUATION In this section, we evaluate our system to the LFW benchmark and a real-world security certification application. Based on our previous observations, we train the whole system with 10,000 most rich individuals. We train the network on four face regions (i.e., centralized at eyebrow, eye center, nose tip, and mouth corner through the facial landmark detector). Fig. 3 presents an overview of the whole system. The final representation of the face is the concatenation on four features and followed by PCA for feature reduction. Training Phase Softmax Raw Image Cropped Patches Naïve CNNs Face Representation PCA Testing Phase Multi-class Classification L2 Distance Figure 3. Overview of Megvii Face Recognition System. We design a simple 10 layers deep convolutional neural network for recognition. Four face regions are cropped for representation extraction. We train our networks on the MFC database under the traditional multi-class classification framework. In testing phase, a PCA model is applied for feature reduction, and a simple L2 norm is used for measuring the pair of testing faces Results on the LFW benchmark We achieve 99.50% accuracy on the LFW benchmark, which is the best result now and beyond human performance. Fig. 4 shows all failed cases in our system. Except for a few pairs (referred to as easy cases ), most cases are considerably hard to distinguish, even from a human. These hard cases suffer from several different cross factors, such as large pose variation, heavy make-up, glass wearing, or other occlusions. We indicate that, without other priors (e.g., We have watched The Hours, so we know that brown hair Virginia Woolf is Nicole Kidman), it s very hard to correct the most remain pairs. Based on this, we think a reasonable upper limit of LFW is about 99.7% if all the easy cases are solved Results on the real-world application In order to investigate the recognition system s performance in real-world environment, we introduce a new benchmark, referred to as Chinese ID (CHID) benchmark. We collect the dataset offline and specialize on Chinese people. Different from the LFW benchmark, CHID benchmark is a domain-specific task to Chinese people. And we are interested in the true positive rate when we keep false positive in a very low rate (e.g., FP = 10 5 ). This benchmark is intended to mimic a real security certification environment and test recognition systems performance. When we apply our 99.50% recognition system to the CHID benchmark, the performance does not meet the real application s requirements. The beyond human system does not really work as it seems. When we keep the false positive rate in 10 5, the true positive rate is 66%. Fig. 5 shows some failed cases in FP = 10 5 criteria. The age variation, including intra-variation (i.e., same person s faces captured in different age) and inter-variation (i.e., people with different ages), 3

4 (a) Easy Cases (b) Hard Cases Pose Occlusion Pose Makeup Errata Occlusion Figure Failed Cases in the LFW benchmark. We present all the failed cases, and group them into two parts. (a) shows the failed cases regarded as easy cases, which we believe can be solved with a better training system under the existing framework. (b) shows the hard cases. These cases all present some special cross factors, such as occlusion, pose variation, or heavy make-up. Most of them are even hard for human. Hence, we believe that without any other priors, it is hard for computer to correct these cases. is a typical characteristic in the CHID benchmark. Unsurprisingly, the system suffers from this variation, because they are not captured in the web-collected MFC database. We do human test on all of our failed cases. After averaging 10 independent results, it shows 90% cases can be solved by human, which means the machine recognition performance is still far from human level in this scenario. can only provide a starting point; it is a baseline for face recognition. Most web-collected faces come from celebrities: smiling, make-up, young, and beautiful. It is far from images captured in the daily life. Despite the high accuracy in the LFW benchmark, its performance still hardly meets the requirements in real-world application. Very low false positive rate. Real-world face recognition has much more diverse criteria than we treated in previous recognition benchmarks. As we state before, in most security certification scenario, customers concern more about the true positive rate when false positive is kept in a very low rate. Although we achieve very high accuracy in LFW benchmark, our system is still far from human performance in these real-world setting. Cross factors. Throughout the failed case study on the LFW and CHID benchmark, pose, occlusion, and age variation are most common factors which influence the system s 6. CHALLENGES LYING AHEAD Based on our evaluation on two benchmarks, here we summarize three main challenges to the face recognition. Data bias. The distribution of web-collected data is extremely unbalanced. Our experiments show a amount of people with few instances per individual do not work in a simple multi-class classification framework. On the other hand, we realize that large-scale web-collected data 4

5 thesize data, especially in modeling physical factors. One of our observations is that the long-tail effect exists in the simple multi-class classification framework. How to use long-tail web-collected data effectively is an interesting issue in the future. Moreover, how to transfer a generic recognition system into a domain-specific application is still a open question. This report provides our industrial view on face recognition, and we hope our experiments and observations will stimulate discussion in the community, both academic and industrial, and improve face recognition technique further. References [1] T. Berg and P. N. Belhumeur. Tom-vs-pete classifiers and identity-preserving alignment for face verification. In BMVC, volume 2, page 7. Citeseer, Figure 5. Some Failed Cases in the CHID Benchmark. The recognition system suffers from the age variations in the CHID benchmark, including intra-variation (i.e., same person s faces captured in different age) and inter-variation (i.e., people with different ages). Because little age variation is captured by the web-collected data, not surprisingly, the system cannot well handle this variation. Indeed, we do human test on all these failed cases. Results show that 90% failed cases can be solved by human. There still exists a big gap between machine recognition and human level. [2] X. Cao, D. Wipf, F. Wen, G. Duan, and J. Sun. A practical transfer learning algorithm for face verification. In Computer Vision (ICCV), 2013 IEEE International Conference on, pages IEEE, [3] Z. Cao, Q. Yin, X. Tang, and J. Sun. Face recognition with learning-based descriptor. In Computer Vision and Pattern Recognition (CVPR), 2010 IEEE Conference on, pages IEEE, [4] D. Chen, X. Cao, L. Wang, F. Wen, and J. Sun. Bayesian face revisited: A joint formulation. In Computer Vision ECCV 2012, pages Springer, [5] D. Chen, X. Cao, F. Wen, and J. Sun. Blessing of dimensionality: Highdimensional feature and its efficient compression for face verification. In Computer Vision and Pattern Recognition (CVPR), 2013 IEEE Conference on, pages IEEE, [6] A. Georghiades, P. Belhumeur, and D. Kriegman. From few to many: Illumination cone models for face recognition under variable lighting and pose. IEEE Trans. Pattern Anal. Mach. Intelligence, 23(6): , performance. However, we still lack a sufficient investigation on these cross factors, and also lack a efficient method to handle them clearly and comprehensively. [7] R. Gross, I. Matthews, J. Cohn, T. Kanade, and S. Baker. Multi-pie. Image and Vision Computing, 28(5): , [8] G. B. Huang, M. Ramesh, T. Berg, and E. Learned-Miller. Labeled faces in the wild: A database for studying face recognition in unconstrained environments. Technical Report 07-49, University of Massachusetts, Amherst, October FUTURE WORKS [9] C. Lu and X. Tang. Surpassing human-level face verification performance on lfw with gaussianface. arxiv preprint arxiv: , Large amounts of web-collected data help us achieve the state-of-the-art result on the LFW benchmark, surpassing the human performance. But this is just a new starting point of face recognition. The significance of this result is to show that face recognition is able to go out of laboratories and come into our daily life. When we are facing the real-work application instead of a simple benchmark, there are still a lot of works we have to do. Our experiments do emphasize that data is an important factor in the recognition system. And we present following issues as an industrial perspective to the expect of future research in face recognition. On one hand, developing more smart and efficient methods mining domain-specific data is one of the important ways to improve performance. For example, video is one of data sources which can provide tremendous amounts of data with spontaneous weakly-labeled faces, but we have not explored completely and applied them to the large-scale face recognition yet. On the other hand, data synthesize is another direction to generate more data. For example, it is very hard to collect data with intra-person age variation manually. So a reliable age variation generator may help a lot. 3D face reconstruction is also a powerful tool to syn- [10] Y. Sun, Y. Chen, X. Wang, and X. Tang. Deep learning face representation by joint identification-verification. In Advances in Neural Information Processing Systems, pages , [11] Y. Sun, X. Wang, and X. Tang. Hybrid deep learning for face verification. In Computer Vision (ICCV), 2013 IEEE International Conference on, pages IEEE, [12] Y. Sun, X. Wang, and X. Tang. Deep learning face representation from predicting 10,000 classes. In Computer Vision and Pattern Recognition (CVPR), 2014 IEEE Conference on, pages IEEE, [13] Y. Sun, X. Wang, and X. Tang. Deeply learned face representations are sparse, selective, and robust. arxiv preprint arxiv: , [14] Y. Taigman, M. Yang, M. Ranzato, and L. Wolf. Deepface: Closing the gap to human-level performance in face verification. In Computer Vision and Pattern Recognition (CVPR), 2014 IEEE Conference on, pages IEEE, [15] Z. Yan, V. Jagadeesh, D. DeCoste, W. Di, and R. Piramuthu. Hd-cnn: Hierarchical deep convolutional neural network for image classification. arxiv preprint arxiv: , [16] Q. Yin, X. Tang, and J. Sun. An associate-predict model for face recognition. In Computer Vision and Pattern Recognition (CVPR), 2011 IEEE Conference on, pages IEEE, [17] Z. Zhu, P. Luo, X. Wang, and X. Tang. Recover canonical-view faces in the wild with deep neural networks. arxiv preprint arxiv: ,

Deep Learning Face Representation by Joint Identification-Verification

Deep Learning Face Representation by Joint Identification-Verification Deep Learning Face Representation by Joint Identification-Verification Yi Sun 1 Yuheng Chen 2 Xiaogang Wang 3,4 Xiaoou Tang 1,4 1 Department of Information Engineering, The Chinese University of Hong Kong

More information

Blessing of Dimensionality: High-dimensional Feature and Its Efficient Compression for Face Verification

Blessing of Dimensionality: High-dimensional Feature and Its Efficient Compression for Face Verification Blessing of Dimensionality: High-dimensional Feature and Its Efficient Compression for Face Verification Dong Chen Xudong Cao Fang Wen Jian Sun University of Science and Technology of China Microsoft Research

More information

Learning Deep Face Representation

Learning Deep Face Representation Learning Deep Face Representation Haoqiang Fan Megvii Inc. fhq@megvii.com Zhimin Cao Megvii Inc. czm@megvii.com Yuning Jiang Megvii Inc. jyn@megvii.com Qi Yin Megvii Inc. yq@megvii.com Chinchilla Doudou

More information

Face Recognition using SIFT Features

Face Recognition using SIFT Features Face Recognition using SIFT Features Mohamed Aly CNS186 Term Project Winter 2006 Abstract Face recognition has many important practical applications, like surveillance and access control.

More information

ATTRIBUTE ENHANCED SPARSE CODING FOR FACE IMAGE RETRIEVAL

ATTRIBUTE ENHANCED SPARSE CODING FOR FACE IMAGE RETRIEVAL ISSN:2320-0790 ATTRIBUTE ENHANCED SPARSE CODING FOR FACE IMAGE RETRIEVAL MILU SAYED, LIYA NOUSHEER PG Research Scholar, ICET ABSTRACT: Content based face image retrieval is an emerging technology. It s

More information

DeepFace: Closing the Gap to Human-Level Performance in Face Verification

DeepFace: Closing the Gap to Human-Level Performance in Face Verification DeepFace: Closing the Gap to Human-Level Performance in Face Verification Yaniv Taigman Ming Yang Marc Aurelio Ranzato Facebook AI Research Menlo Park, CA, USA {yaniv, mingyang, ranzato}@fb.com Lior Wolf

More information

High-Fidelity Pose and Expression Normalization for Face Recognition in the Wild

High-Fidelity Pose and Expression Normalization for Face Recognition in the Wild High-Fidelity Pose and Expression Normalization for Face Recognition in the Wild Xiangyu Zhu Zhen Lei Junjie Yan Dong Yi Stan Z. Li Center for Biometrics and Security Research & National Laboratory of

More information

Pedestrian Detection with RCNN

Pedestrian Detection with RCNN Pedestrian Detection with RCNN Matthew Chen Department of Computer Science Stanford University mcc17@stanford.edu Abstract In this paper we evaluate the effectiveness of using a Region-based Convolutional

More information

Extensive Facial Landmark Localization with Coarse-to-fine Convolutional Network Cascade

Extensive Facial Landmark Localization with Coarse-to-fine Convolutional Network Cascade Extensive Facial Landmark Localization with Coarse-to-fine Convolutional Network Cascade Erjin Zhou Haoqiang Fan Zhimin Cao Yuning Jiang Qi Yin Megvii Inc. {zej,fhq,czm,jyn,yq}@megvii.com Abstract We present

More information

DeepFace: Closing the Gap to Human-Level Performance in Face Verification

DeepFace: Closing the Gap to Human-Level Performance in Face Verification DeepFace: Closing the Gap to Human-Level Performance in Face Verification Yaniv Taigman Ming Yang Marc Aurelio Ranzato Facebook AI Group Menlo Park, CA, USA {yaniv, mingyang, ranzato}@fb.com Lior Wolf

More information

Novelty Detection in image recognition using IRF Neural Networks properties

Novelty Detection in image recognition using IRF Neural Networks properties Novelty Detection in image recognition using IRF Neural Networks properties Philippe Smagghe, Jean-Luc Buessler, Jean-Philippe Urban Université de Haute-Alsace MIPS 4, rue des Frères Lumière, 68093 Mulhouse,

More information

Face Recognition For Remote Database Backup System

Face Recognition For Remote Database Backup System Face Recognition For Remote Database Backup System Aniza Mohamed Din, Faudziah Ahmad, Mohamad Farhan Mohamad Mohsin, Ku Ruhana Ku-Mahamud, Mustafa Mufawak Theab 2 Graduate Department of Computer Science,UUM

More information

AN IMPROVED DOUBLE CODING LOCAL BINARY PATTERN ALGORITHM FOR FACE RECOGNITION

AN IMPROVED DOUBLE CODING LOCAL BINARY PATTERN ALGORITHM FOR FACE RECOGNITION AN IMPROVED DOUBLE CODING LOCAL BINARY PATTERN ALGORITHM FOR FACE RECOGNITION Saurabh Asija 1, Rakesh Singh 2 1 Research Scholar (Computer Engineering Department), Punjabi University, Patiala. 2 Asst.

More information

6.2.8 Neural networks for data mining

6.2.8 Neural networks for data mining 6.2.8 Neural networks for data mining Walter Kosters 1 In many application areas neural networks are known to be valuable tools. This also holds for data mining. In this chapter we discuss the use of neural

More information

Image Normalization for Illumination Compensation in Facial Images

Image Normalization for Illumination Compensation in Facial Images Image Normalization for Illumination Compensation in Facial Images by Martin D. Levine, Maulin R. Gandhi, Jisnu Bhattacharyya Department of Electrical & Computer Engineering & Center for Intelligent Machines

More information

Illumination, Expression and Occlusion Invariant Pose-Adaptive Face Recognition System for Real- Time Applications

Illumination, Expression and Occlusion Invariant Pose-Adaptive Face Recognition System for Real- Time Applications Illumination, Expression and Occlusion Invariant Pose-Adaptive Face Recognition System for Real- Time Applications Shireesha Chintalapati #1, M. V. Raghunadh *2 Department of E and CE NIT Warangal, Andhra

More information

Unconstrained Facial Images: Database for Face Recognition under Real-world Conditions

Unconstrained Facial Images: Database for Face Recognition under Real-world Conditions Unconstrained Facial Images: Database for Face Recognition under Real-world Conditions Ladislav Lenc 1,2 and Pavel Král 1,2 1 Dept. of Computer Science & Engineering University of West Bohemia Plzeň, Czech

More information

What is the Right Illumination Normalization for Face Recognition?

What is the Right Illumination Normalization for Face Recognition? What is the Right Illumination Normalization for Face Recognition? Aishat Mahmoud Dan-ali Department of Computer Science and Engineering The American University in Cairo AUC Avenue, P.O. Box 74, New Cairo

More information

Recognizing Cats and Dogs with Shape and Appearance based Models. Group Member: Chu Wang, Landu Jiang

Recognizing Cats and Dogs with Shape and Appearance based Models. Group Member: Chu Wang, Landu Jiang Recognizing Cats and Dogs with Shape and Appearance based Models Group Member: Chu Wang, Landu Jiang Abstract Recognizing cats and dogs from images is a challenging competition raised by Kaggle platform

More information

Lecture 6: CNNs for Detection, Tracking, and Segmentation Object Detection

Lecture 6: CNNs for Detection, Tracking, and Segmentation Object Detection CSED703R: Deep Learning for Visual Recognition (206S) Lecture 6: CNNs for Detection, Tracking, and Segmentation Object Detection Bohyung Han Computer Vision Lab. bhhan@postech.ac.kr 2 3 Object detection

More information

Image Classification for Dogs and Cats

Image Classification for Dogs and Cats Image Classification for Dogs and Cats Bang Liu, Yan Liu Department of Electrical and Computer Engineering {bang3,yan10}@ualberta.ca Kai Zhou Department of Computing Science kzhou3@ualberta.ca Abstract

More information

SYMMETRIC EIGENFACES MILI I. SHAH

SYMMETRIC EIGENFACES MILI I. SHAH SYMMETRIC EIGENFACES MILI I. SHAH Abstract. Over the years, mathematicians and computer scientists have produced an extensive body of work in the area of facial analysis. Several facial analysis algorithms

More information

Distributed forests for MapReduce-based machine learning

Distributed forests for MapReduce-based machine learning Distributed forests for MapReduce-based machine learning Ryoji Wakayama, Ryuei Murata, Akisato Kimura, Takayoshi Yamashita, Yuji Yamauchi, Hironobu Fujiyoshi Chubu University, Japan. NTT Communication

More information

Predict Influencers in the Social Network

Predict Influencers in the Social Network Predict Influencers in the Social Network Ruishan Liu, Yang Zhao and Liuyu Zhou Email: rliu2, yzhao2, lyzhou@stanford.edu Department of Electrical Engineering, Stanford University Abstract Given two persons

More information

Resampling for Face Recognition

Resampling for Face Recognition Resampling for Face Recognition Xiaoguang Lu and Anil K. Jain Dept. of Computer Science & Engineering, Michigan State University East Lansing, MI 48824 {lvxiaogu,jain}@cse.msu.edu Abstract. A number of

More information

Mood Detection: Implementing a facial expression recognition system

Mood Detection: Implementing a facial expression recognition system Mood Detection: Implementing a facial expression recognition system Neeraj Agrawal, Rob Cosgriff and Ritvik Mudur 1. Introduction Facial expressions play a significant role in human dialogue. As a result,

More information

Tracking in flussi video 3D. Ing. Samuele Salti

Tracking in flussi video 3D. Ing. Samuele Salti Seminari XXIII ciclo Tracking in flussi video 3D Ing. Tutors: Prof. Tullio Salmon Cinotti Prof. Luigi Di Stefano The Tracking problem Detection Object model, Track initiation, Track termination, Tracking

More information

Bert Huang Department of Computer Science Virginia Tech

Bert Huang Department of Computer Science Virginia Tech This paper was submitted as a final project report for CS6424/ECE6424 Probabilistic Graphical Models and Structured Prediction in the spring semester of 2016. The work presented here is done by students

More information

CS229 Project Final Report. Sign Language Gesture Recognition with Unsupervised Feature Learning

CS229 Project Final Report. Sign Language Gesture Recognition with Unsupervised Feature Learning CS229 Project Final Report Sign Language Gesture Recognition with Unsupervised Feature Learning Justin K. Chen, Debabrata Sengupta, Rukmani Ravi Sundaram 1. Introduction The problem we are investigating

More information

Chapter 6. The stacking ensemble approach

Chapter 6. The stacking ensemble approach 82 This chapter proposes the stacking ensemble approach for combining different data mining classifiers to get better performance. Other combination techniques like voting, bagging etc are also described

More information

ENHANCED WEB IMAGE RE-RANKING USING SEMANTIC SIGNATURES

ENHANCED WEB IMAGE RE-RANKING USING SEMANTIC SIGNATURES International Journal of Computer Engineering & Technology (IJCET) Volume 7, Issue 2, March-April 2016, pp. 24 29, Article ID: IJCET_07_02_003 Available online at http://www.iaeme.com/ijcet/issues.asp?jtype=ijcet&vtype=7&itype=2

More information

LOGISTIC SIMILARITY METRIC LEARNING FOR FACE VERIFICATION

LOGISTIC SIMILARITY METRIC LEARNING FOR FACE VERIFICATION LOGISIC SIMILARIY MERIC LEARNING FOR FACE VERIFICAION Lilei Zheng, Khalid Idrissi, Christophe Garcia, Stefan Duffner and Atilla Baskurt Université de Lyon, CNRS, INSA-Lyon, LIRIS, UMR5205, F-69621, France

More information

Online Learning in Biometrics: A Case Study in Face Classifier Update

Online Learning in Biometrics: A Case Study in Face Classifier Update Online Learning in Biometrics: A Case Study in Face Classifier Update Richa Singh, Mayank Vatsa, Arun Ross, and Afzel Noore Abstract In large scale applications, hundreds of new subjects may be regularly

More information

Unsupervised Joint Alignment of Complex Images

Unsupervised Joint Alignment of Complex Images Unsupervised Joint Alignment of Complex Images Gary B. Huang Vidit Jain University of Massachusetts Amherst Amherst, MA {gbhuang,vidit,elm}@cs.umass.edu Erik Learned-Miller Abstract Many recognition algorithms

More information

Designing and Testing an Anonymous Face Recognition System

Designing and Testing an Anonymous Face Recognition System Designing and Testing an Anonymous Face Recognition System Joris Diesvelt University of Twente P.O. Box 217, 7500AE Enschede The Netherlands j.j.diesvelt@student.utwente.nl ABSTRACT This paper contains

More information

BEHAVIOR BASED CREDIT CARD FRAUD DETECTION USING SUPPORT VECTOR MACHINES

BEHAVIOR BASED CREDIT CARD FRAUD DETECTION USING SUPPORT VECTOR MACHINES BEHAVIOR BASED CREDIT CARD FRAUD DETECTION USING SUPPORT VECTOR MACHINES 123 CHAPTER 7 BEHAVIOR BASED CREDIT CARD FRAUD DETECTION USING SUPPORT VECTOR MACHINES 7.1 Introduction Even though using SVM presents

More information

Classifying Manipulation Primitives from Visual Data

Classifying Manipulation Primitives from Visual Data Classifying Manipulation Primitives from Visual Data Sandy Huang and Dylan Hadfield-Menell Abstract One approach to learning from demonstrations in robotics is to make use of a classifier to predict if

More information

Face Recognition in Low-resolution Images by Using Local Zernike Moments

Face Recognition in Low-resolution Images by Using Local Zernike Moments Proceedings of the International Conference on Machine Vision and Machine Learning Prague, Czech Republic, August14-15, 014 Paper No. 15 Face Recognition in Low-resolution Images by Using Local Zernie

More information

Structured Face Hallucination

Structured Face Hallucination Structured Face Hallucination Chih-Yuan Yang Sifei Liu Ming-Hsuan Yang Electrical Engineering and Computer Science University of California at Merced {cyang35, sliu32, mhyang}@ucmerced.edu Abstract The

More information

Deformable Part Models with CNN Features

Deformable Part Models with CNN Features Deformable Part Models with CNN Features Pierre-André Savalle 1, Stavros Tsogkas 1,2, George Papandreou 3, Iasonas Kokkinos 1,2 1 Ecole Centrale Paris, 2 INRIA, 3 TTI-Chicago Abstract. In this work we

More information

Unlock Screen Application Design Using Face Expression on Android Smartphone

Unlock Screen Application Design Using Face Expression on Android Smartphone Unlock Screen Application Design Using Face Expression on Android Smartphone Rhio Sutoyo, Jeklin Harefa, Alexander, Andry Chowanda Bina Nusantara University, Jakarta, Indonesia Abstract. Nowadays, smartphone

More information

The Scientific Data Mining Process

The Scientific Data Mining Process Chapter 4 The Scientific Data Mining Process When I use a word, Humpty Dumpty said, in rather a scornful tone, it means just what I choose it to mean neither more nor less. Lewis Carroll [87, p. 214] In

More information

LOCAL SURFACE PATCH BASED TIME ATTENDANCE SYSTEM USING FACE. indhubatchvsa@gmail.com

LOCAL SURFACE PATCH BASED TIME ATTENDANCE SYSTEM USING FACE. indhubatchvsa@gmail.com LOCAL SURFACE PATCH BASED TIME ATTENDANCE SYSTEM USING FACE 1 S.Manikandan, 2 S.Abirami, 2 R.Indumathi, 2 R.Nandhini, 2 T.Nanthini 1 Assistant Professor, VSA group of institution, Salem. 2 BE(ECE), VSA

More information

Biometric Authentication using Online Signatures

Biometric Authentication using Online Signatures Biometric Authentication using Online Signatures Alisher Kholmatov and Berrin Yanikoglu alisher@su.sabanciuniv.edu, berrin@sabanciuniv.edu http://fens.sabanciuniv.edu Sabanci University, Tuzla, Istanbul,

More information

Published by: PIONEER RESEARCH & DEVELOPMENT GROUP (www.prdg.org) 1 Robust Facial Expression Recognition

Published by: PIONEER RESEARCH & DEVELOPMENT GROUP (www.prdg.org) 1 Robust Facial Expression Recognition Robust Facial Expression Recognition Mr. Mukund Kumar 1, Ms. D. Udaya 2 1, 2 Computer Science and Engineering, Dr. Pauls Engineering College,Villupuram Abstract This paper proposes a novel local feature

More information

Supporting Online Material for

Supporting Online Material for www.sciencemag.org/cgi/content/full/313/5786/504/dc1 Supporting Online Material for Reducing the Dimensionality of Data with Neural Networks G. E. Hinton* and R. R. Salakhutdinov *To whom correspondence

More information

2014/02/13 Sphinx Lunch

2014/02/13 Sphinx Lunch 2014/02/13 Sphinx Lunch Best Student Paper Award @ 2013 IEEE Workshop on Automatic Speech Recognition and Understanding Dec. 9-12, 2013 Unsupervised Induction and Filling of Semantic Slot for Spoken Dialogue

More information

A Learning Based Method for Super-Resolution of Low Resolution Images

A Learning Based Method for Super-Resolution of Low Resolution Images A Learning Based Method for Super-Resolution of Low Resolution Images Emre Ugur June 1, 2004 emre.ugur@ceng.metu.edu.tr Abstract The main objective of this project is the study of a learning based method

More information

Introduction to Deep Learning and its applications in Computer Vision

Introduction to Deep Learning and its applications in Computer Vision Introduction to Deep Learning and its applications in Computer Vision Xiaogang Wang Department of Electronic Engineering, The Chinese University of Hong Kong Morning Tutorial (9:00 12:30) March 23, 2015

More information

Human Pose Estimation and Activity Classification Using Convolutional Neural Networks

Human Pose Estimation and Activity Classification Using Convolutional Neural Networks Human Pose Estimation and Activity Classification Using Convolutional Neural Networks Amy Bearman Stanford University Catherine Dong Stanford University abearman@cs.stanford.edu cdong@cs.stanford.edu Abstract

More information

Face Recognition using Principle Component Analysis

Face Recognition using Principle Component Analysis Face Recognition using Principle Component Analysis Kyungnam Kim Department of Computer Science University of Maryland, College Park MD 20742, USA Summary This is the summary of the basic idea about PCA

More information

Simple and efficient online algorithms for real world applications

Simple and efficient online algorithms for real world applications Simple and efficient online algorithms for real world applications Università degli Studi di Milano Milano, Italy Talk @ Centro de Visión por Computador Something about me PhD in Robotics at LIRA-Lab,

More information

Intrusion Detection via Machine Learning for SCADA System Protection

Intrusion Detection via Machine Learning for SCADA System Protection Intrusion Detection via Machine Learning for SCADA System Protection S.L.P. Yasakethu Department of Computing, University of Surrey, Guildford, GU2 7XH, UK. s.l.yasakethu@surrey.ac.uk J. Jiang Department

More information

Categorical Data Visualization and Clustering Using Subjective Factors

Categorical Data Visualization and Clustering Using Subjective Factors Categorical Data Visualization and Clustering Using Subjective Factors Chia-Hui Chang and Zhi-Kai Ding Department of Computer Science and Information Engineering, National Central University, Chung-Li,

More information

Image and Video Understanding

Image and Video Understanding Image and Video Understanding 2VO 710.095 WS Christoph Feichtenhofer, Axel Pinz Slide credits: Many thanks to all the great computer vision researchers on which this presentation relies on. Most material

More information

Eyeglass Localization for Low Resolution Images

Eyeglass Localization for Low Resolution Images Eyeglass Localization for Low Resolution Images Earl Arvin Calapatia 1 1 De La Salle University 1 earl_calapatia@dlsu.ph Abstract: Facial data is a necessity in facial image processing technologies. In

More information

Machine Learning for Data Science (CS4786) Lecture 1

Machine Learning for Data Science (CS4786) Lecture 1 Machine Learning for Data Science (CS4786) Lecture 1 Tu-Th 10:10 to 11:25 AM Hollister B14 Instructors : Lillian Lee and Karthik Sridharan ROUGH DETAILS ABOUT THE COURSE Diagnostic assignment 0 is out:

More information

Feature Engineering in Machine Learning

Feature Engineering in Machine Learning Research Fellow Faculty of Information Technology, Monash University, Melbourne VIC 3800, Australia August 21, 2015 Outline A Machine Learning Primer Machine Learning and Data Science Bias-Variance Phenomenon

More information

Behavior Analysis in Crowded Environments. XiaogangWang Department of Electronic Engineering The Chinese University of Hong Kong June 25, 2011

Behavior Analysis in Crowded Environments. XiaogangWang Department of Electronic Engineering The Chinese University of Hong Kong June 25, 2011 Behavior Analysis in Crowded Environments XiaogangWang Department of Electronic Engineering The Chinese University of Hong Kong June 25, 2011 Behavior Analysis in Sparse Scenes Zelnik-Manor & Irani CVPR

More information

Creating a Big Data Resource from the Faces of Wikipedia

Creating a Big Data Resource from the Faces of Wikipedia Creating a Big Data Resource from the Faces of Wikipedia Md. Kamrul Hasan Génie informatique et génie logiciel École Polytechnique de Montreal Québec, Canada md-kamrul.hasan@polymtl.ca Christopher J. Pal

More information

FACE RECOGNITION USING FEATURE EXTRACTION AND NEURO-FUZZY TECHNIQUES

FACE RECOGNITION USING FEATURE EXTRACTION AND NEURO-FUZZY TECHNIQUES International Journal of Electronics and Computer Science Engineering 2048 Available Online at www.ijecse.org ISSN : 2277-1956 FACE RECOGNITION USING FEATURE EXTRACTION AND NEURO-FUZZY TECHNIQUES Ritesh

More information

A Comparison of Photometric Normalisation Algorithms for Face Verification

A Comparison of Photometric Normalisation Algorithms for Face Verification A Comparison of Photometric Normalisation Algorithms for Face Verification James Short, Josef Kittler and Kieron Messer Centre for Vision, Speech and Signal Processing University of Surrey Guildford, Surrey,

More information

The Delicate Art of Flower Classification

The Delicate Art of Flower Classification The Delicate Art of Flower Classification Paul Vicol Simon Fraser University University Burnaby, BC pvicol@sfu.ca Note: The following is my contribution to a group project for a graduate machine learning

More information

TIETS34 Seminar: Data Mining on Biometric identification

TIETS34 Seminar: Data Mining on Biometric identification TIETS34 Seminar: Data Mining on Biometric identification Youming Zhang Computer Science, School of Information Sciences, 33014 University of Tampere, Finland Youming.Zhang@uta.fi Course Description Content

More information

EM Clustering Approach for Multi-Dimensional Analysis of Big Data Set

EM Clustering Approach for Multi-Dimensional Analysis of Big Data Set EM Clustering Approach for Multi-Dimensional Analysis of Big Data Set Amhmed A. Bhih School of Electrical and Electronic Engineering Princy Johnson School of Electrical and Electronic Engineering Martin

More information

Steven C.H. Hoi School of Information Systems Singapore Management University Email: chhoi@smu.edu.sg

Steven C.H. Hoi School of Information Systems Singapore Management University Email: chhoi@smu.edu.sg Steven C.H. Hoi School of Information Systems Singapore Management University Email: chhoi@smu.edu.sg Introduction http://stevenhoi.org/ Finance Recommender Systems Cyber Security Machine Learning Visual

More information

MACHINE LEARNING BASICS WITH R

MACHINE LEARNING BASICS WITH R MACHINE LEARNING [Hands-on Introduction of Supervised Machine Learning Methods] DURATION 2 DAY The field of machine learning is concerned with the question of how to construct computer programs that automatically

More information

Transform-based Domain Adaptation for Big Data

Transform-based Domain Adaptation for Big Data Transform-based Domain Adaptation for Big Data Erik Rodner University of Jena Judy Hoffman Jeff Donahue Trevor Darrell Kate Saenko UMass Lowell Abstract Images seen during test time are often not from

More information

Face Alignment by Explicit Shape Regression

Face Alignment by Explicit Shape Regression Face Alignment by Explicit Shape Regression Xudong Cao Yichen Wei Fang Wen Jian Sun Microsoft Research Asia {xudongca,yichenw,fangwen,jiansun}@microsoft.com Abstract. We present a very efficient, highly

More information

Computer Vision Visual Recognition Alexander C. Berg

Computer Vision Visual Recognition Alexander C. Berg Research Statement Computer Vision Visual Recognition Alexander C. Berg Computational visual recognition concerns identifying what is in an image, video, or other visual data, enabling applications such

More information

lop Building Machine Learning Systems with Python en source

lop Building Machine Learning Systems with Python en source Building Machine Learning Systems with Python Master the art of machine learning with Python and build effective machine learning systems with this intensive handson guide Willi Richert Luis Pedro Coelho

More information

Classification of Fine Art Oil Paintings by Semantic Category

Classification of Fine Art Oil Paintings by Semantic Category Classification of Fine Art Oil Paintings by Semantic Category William Kromydas kromydas@stanford.edu Abstract In this paper we explore supervised learning techniques that are able to classify fine-art

More information

A comparative study on face recognition techniques and neural network

A comparative study on face recognition techniques and neural network A comparative study on face recognition techniques and neural network 1. Abstract Meftah Ur Rahman Department of Computer Science George Mason University mrahma12@masonlive.gmu.edu In modern times, face

More information

CS 2750 Machine Learning. Lecture 1. Machine Learning. http://www.cs.pitt.edu/~milos/courses/cs2750/ CS 2750 Machine Learning.

CS 2750 Machine Learning. Lecture 1. Machine Learning. http://www.cs.pitt.edu/~milos/courses/cs2750/ CS 2750 Machine Learning. Lecture Machine Learning Milos Hauskrecht milos@cs.pitt.edu 539 Sennott Square, x5 http://www.cs.pitt.edu/~milos/courses/cs75/ Administration Instructor: Milos Hauskrecht milos@cs.pitt.edu 539 Sennott

More information

Deep Fisher Networks and Class Saliency Maps for Object Classification and Localisation

Deep Fisher Networks and Class Saliency Maps for Object Classification and Localisation Deep Fisher Networks and Class Saliency Maps for Object Classification and Localisation Karén Simonyan, Andrea Vedaldi, Andrew Zisserman Visual Geometry Group, University of Oxford Outline Classification

More information

Class Imbalance Learning in Software Defect Prediction

Class Imbalance Learning in Software Defect Prediction Class Imbalance Learning in Software Defect Prediction Dr. Shuo Wang s.wang@cs.bham.ac.uk University of Birmingham Research keywords: ensemble learning, class imbalance learning, online learning Shuo Wang

More information

MALLET-Privacy Preserving Influencer Mining in Social Media Networks via Hypergraph

MALLET-Privacy Preserving Influencer Mining in Social Media Networks via Hypergraph MALLET-Privacy Preserving Influencer Mining in Social Media Networks via Hypergraph Janani K 1, Narmatha S 2 Assistant Professor, Department of Computer Science and Engineering, Sri Shakthi Institute of

More information

W6.B.1. FAQs CS535 BIG DATA W6.B.3. 4. If the distance of the point is additionally less than the tight distance T 2, remove it from the original set

W6.B.1. FAQs CS535 BIG DATA W6.B.3. 4. If the distance of the point is additionally less than the tight distance T 2, remove it from the original set http://wwwcscolostateedu/~cs535 W6B W6B2 CS535 BIG DAA FAQs Please prepare for the last minute rush Store your output files safely Partial score will be given for the output from less than 50GB input Computer

More information

Adaptive Face Recognition System from Myanmar NRC Card

Adaptive Face Recognition System from Myanmar NRC Card Adaptive Face Recognition System from Myanmar NRC Card Ei Phyo Wai University of Computer Studies, Yangon, Myanmar Myint Myint Sein University of Computer Studies, Yangon, Myanmar ABSTRACT Biometrics is

More information

Distance Metric Learning in Data Mining (Part I) Fei Wang and Jimeng Sun IBM TJ Watson Research Center

Distance Metric Learning in Data Mining (Part I) Fei Wang and Jimeng Sun IBM TJ Watson Research Center Distance Metric Learning in Data Mining (Part I) Fei Wang and Jimeng Sun IBM TJ Watson Research Center 1 Outline Part I - Applications Motivation and Introduction Patient similarity application Part II

More information

Interpreting hand-over-face gestures

Interpreting hand-over-face gestures Interpreting hand-over-face gestures Marwa Mahmoud and Peter Robinson University of Cambridge Abstract. People often hold their hands near their faces as a gesture in natural conversation, which can interfere

More information

MS1b Statistical Data Mining

MS1b Statistical Data Mining MS1b Statistical Data Mining Yee Whye Teh Department of Statistics Oxford http://www.stats.ox.ac.uk/~teh/datamining.html Outline Administrivia and Introduction Course Structure Syllabus Introduction to

More information

Face Model Fitting on Low Resolution Images

Face Model Fitting on Low Resolution Images Face Model Fitting on Low Resolution Images Xiaoming Liu Peter H. Tu Frederick W. Wheeler Visualization and Computer Vision Lab General Electric Global Research Center Niskayuna, NY, 1239, USA {liux,tu,wheeler}@research.ge.com

More information

Clustering Big Data. Anil K. Jain. (with Radha Chitta and Rong Jin) Department of Computer Science Michigan State University November 29, 2012

Clustering Big Data. Anil K. Jain. (with Radha Chitta and Rong Jin) Department of Computer Science Michigan State University November 29, 2012 Clustering Big Data Anil K. Jain (with Radha Chitta and Rong Jin) Department of Computer Science Michigan State University November 29, 2012 Outline Big Data How to extract information? Data clustering

More information

Machine learning challenges for big data

Machine learning challenges for big data Machine learning challenges for big data Francis Bach SIERRA Project-team, INRIA - Ecole Normale Supérieure Joint work with R. Jenatton, J. Mairal, G. Obozinski, N. Le Roux, M. Schmidt - December 2012

More information

Chapter 8. Final Results on Dutch Senseval-2 Test Data

Chapter 8. Final Results on Dutch Senseval-2 Test Data Chapter 8 Final Results on Dutch Senseval-2 Test Data The general idea of testing is to assess how well a given model works and that can only be done properly on data that has not been seen before. Supervised

More information

Comparison of K-means and Backpropagation Data Mining Algorithms

Comparison of K-means and Backpropagation Data Mining Algorithms Comparison of K-means and Backpropagation Data Mining Algorithms Nitu Mathuriya, Dr. Ashish Bansal Abstract Data mining has got more and more mature as a field of basic research in computer science and

More information

Hong Kong Stock Index Forecasting

Hong Kong Stock Index Forecasting Hong Kong Stock Index Forecasting Tong Fu Shuo Chen Chuanqi Wei tfu1@stanford.edu cslcb@stanford.edu chuanqi@stanford.edu Abstract Prediction of the movement of stock market is a long-time attractive topic

More information

On Multifont Character Classification in Telugu

On Multifont Character Classification in Telugu On Multifont Character Classification in Telugu Venkat Rasagna, K. J. Jinesh, and C. V. Jawahar International Institute of Information Technology, Hyderabad 500032, INDIA. Abstract. A major requirement

More information

Bayesian Face Revisited: A Joint Formulation

Bayesian Face Revisited: A Joint Formulation Bayesian Face Revisited: A Joint Formulation Dong Chen 1, Xudong Cao 3, Liwei Wang 2, Fang Wen 3, and Jian Sun 3 1 University of Science and Technology of China chendong@mail.ustc.edu.cn 2 The Chinese

More information

Application of Machine Learning to Link Prediction

Application of Machine Learning to Link Prediction Application of Machine Learning to Link Prediction Kyle Julian (kjulian3), Wayne Lu (waynelu) December 6, 6 Introduction Real-world networks evolve over time as new nodes and links are added. Link prediction

More information

Evaluation of Feature Selection Methods for Predictive Modeling Using Neural Networks in Credits Scoring

Evaluation of Feature Selection Methods for Predictive Modeling Using Neural Networks in Credits Scoring 714 Evaluation of Feature election Methods for Predictive Modeling Using Neural Networks in Credits coring Raghavendra B. K. Dr. M.G.R. Educational and Research Institute, Chennai-95 Email: raghavendra_bk@rediffmail.com

More information

E-commerce Transaction Anomaly Classification

E-commerce Transaction Anomaly Classification E-commerce Transaction Anomaly Classification Minyong Lee minyong@stanford.edu Seunghee Ham sham12@stanford.edu Qiyi Jiang qjiang@stanford.edu I. INTRODUCTION Due to the increasing popularity of e-commerce

More information

Tattoo Detection for Soft Biometric De-Identification Based on Convolutional NeuralNetworks

Tattoo Detection for Soft Biometric De-Identification Based on Convolutional NeuralNetworks 1 Tattoo Detection for Soft Biometric De-Identification Based on Convolutional NeuralNetworks Tomislav Hrkać, Karla Brkić, Zoran Kalafatić Faculty of Electrical Engineering and Computing University of

More information

CLASSIFYING NETWORK TRAFFIC IN THE BIG DATA ERA

CLASSIFYING NETWORK TRAFFIC IN THE BIG DATA ERA CLASSIFYING NETWORK TRAFFIC IN THE BIG DATA ERA Professor Yang Xiang Network Security and Computing Laboratory (NSCLab) School of Information Technology Deakin University, Melbourne, Australia http://anss.org.au/nsclab

More information

Huan Wang. Education. Working Experience. Fields of Interest

Huan Wang. Education. Working Experience. Fields of Interest Huan Wang Phone: 1-203-936-8878 Email: joyousprince@gmail.com Web: http://cs.yale.edu/homes/wang-huan Education PhD 2013 Supervised by Prof. Daniel A. Spielman, Department of Computer Science, Yale University,

More information

Making Sense of the Mayhem: Machine Learning and March Madness

Making Sense of the Mayhem: Machine Learning and March Madness Making Sense of the Mayhem: Machine Learning and March Madness Alex Tran and Adam Ginzberg Stanford University atran3@stanford.edu ginzberg@stanford.edu I. Introduction III. Model The goal of our research

More information

FACE RECOGNITION BASED ATTENDANCE MARKING SYSTEM

FACE RECOGNITION BASED ATTENDANCE MARKING SYSTEM Available Online at www.ijcsmc.com International Journal of Computer Science and Mobile Computing A Monthly Journal of Computer Science and Information Technology IJCSMC, Vol. 3, Issue. 2, February 2014,

More information

VEHICLE LOCALISATION AND CLASSIFICATION IN URBAN CCTV STREAMS

VEHICLE LOCALISATION AND CLASSIFICATION IN URBAN CCTV STREAMS VEHICLE LOCALISATION AND CLASSIFICATION IN URBAN CCTV STREAMS Norbert Buch 1, Mark Cracknell 2, James Orwell 1 and Sergio A. Velastin 1 1. Kingston University, Penrhyn Road, Kingston upon Thames, KT1 2EE,

More information

Term Discrimination Based Robust Text Classification with Application to Email Spam Filtering. PhD Thesis. Khurum Nazir Junejo 2004-03-0018

Term Discrimination Based Robust Text Classification with Application to Email Spam Filtering. PhD Thesis. Khurum Nazir Junejo 2004-03-0018 Term Discrimination Based Robust Text Classification with Application to Email Spam Filtering PhD Thesis Khurum Nazir Junejo 2004-03-0018 Advisor: Dr. Asim Karim Department of Computer Science Syed Babar

More information